Self-Portraits in JavaScript
In this talk we'll explore three different approaches to facial recognition in the browser to help us ""draw"" a self-portrait using JavaScript. We'll explore appraoches that run entirely on the client-side using TensorFlow.js & other libraries, via web-based services (AWS, Googel Cloud & Azure) and using the new, experimental Shape Detection API.
We'll explore what it's like to work with each approach and what the advantages and trade-offs are. Finally, we'll discuss long-term security implications and ramificiations we should consider as we introduce ourselves to basic machine-learning concepts through this creative exploration.
Speaker Bio
George Mandis is a Google Developer Expert in Web Technologies and independent full stack developer & consultant. He has has spoken and led workshops at a number of conferences including Microsoft Build, FrontMania, C'T WebDev, JSFoo, HolyJS and FullStack London.
